[v7 15/16] selftests/mm/hmm-tests: new throughput tests including THP

[Balbir Singh <balbirs@nvidia.com>]

Add new benchmark style support to test transfer bandwidth for zone device
memory operations.

Cc: David Hildenbrand <david@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: Ying Huang <ying.huang@linux.alibaba.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Mika Penttilä <mpenttil@redhat.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Francois Dugast <francois.dugast@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

Signed-off-by: Balbir Singh <balbirs@nvidia.com>
---
 tools/testing/selftests/mm/hmm-tests.c | 197 ++++++++++++++++++++++++-
 1 file changed, 196 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c
index dedc1049bd4d..5a1525f72daa 100644
--- a/tools/testing/selftests/mm/hmm-tests.c
+++ b/tools/testing/selftests/mm/hmm-tests.c
@@ -25,6 +25,7 @@
 #include <sys/stat.h>
 #include <sys/mman.h>
 #include <sys/ioctl.h>
+#include <sys/time.h>
 
 
 /*
@@ -209,8 +210,10 @@ static void hmm_buffer_free(struct hmm_buffer *buffer)
 	if (buffer == NULL)
 		return;
 
-	if (buffer->ptr)
+	if (buffer->ptr) {
 		munmap(buffer->ptr, buffer->size);
+		buffer->ptr = NULL;
+	}
 	free(buffer->mirror);
 	free(buffer);
 }
@@ -2657,4 +2660,196 @@ TEST_F(hmm, migrate_anon_huge_zero_err)
 	buffer->ptr = old_ptr;
 	hmm_buffer_free(buffer);
 }
+
+struct benchmark_results {
+	double sys_to_dev_time;
+	double dev_to_sys_time;
+	double throughput_s2d;
+	double throughput_d2s;
+};
+
+static double get_time_ms(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000.0) + (tv.tv_usec / 1000.0);
+}
+
+static inline struct hmm_buffer *hmm_buffer_alloc(unsigned long size)
+{
+	struct hmm_buffer *buffer;
+
+	buffer = malloc(sizeof(*buffer));
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	memset(buffer->mirror, 0xFF, size);
+	return buffer;
+}
+
+static void print_benchmark_results(const char *test_name, size_t buffer_size,
+				     struct benchmark_results *thp,
+				     struct benchmark_results *regular)
+{
+	double s2d_improvement = ((regular->sys_to_dev_time - thp->sys_to_dev_time) /
+				 regular->sys_to_dev_time) * 100.0;
+	double d2s_improvement = ((regular->dev_to_sys_time - thp->dev_to_sys_time) /
+				 regular->dev_to_sys_time) * 100.0;
+	double throughput_s2d_improvement = ((thp->throughput_s2d - regular->throughput_s2d) /
+					    regular->throughput_s2d) * 100.0;
+	double throughput_d2s_improvement = ((thp->throughput_d2s - regular->throughput_d2s) /
+					    regular->throughput_d2s) * 100.0;
+
+	printf("\n=== %s (%.1f MB) ===\n", test_name, buffer_size / (1024.0 * 1024.0));
+	printf("                     | With THP        | Without THP     | Improvement\n");
+	printf("---------------------------------------------------------------------\n");
+	printf("Sys->Dev Migration   | %.3f ms        | %.3f ms        | %.1f%%\n",
+	       thp->sys_to_dev_time, regular->sys_to_dev_time, s2d_improvement);
+	printf("Dev->Sys Migration   | %.3f ms        | %.3f ms        | %.1f%%\n",
+	       thp->dev_to_sys_time, regular->dev_to_sys_time, d2s_improvement);
+	printf("S->D Throughput      | %.2f GB/s      | %.2f GB/s      | %.1f%%\n",
+	       thp->throughput_s2d, regular->throughput_s2d, throughput_s2d_improvement);
+	printf("D->S Throughput      | %.2f GB/s      | %.2f GB/s      | %.1f%%\n",
+	       thp->throughput_d2s, regular->throughput_d2s, throughput_d2s_improvement);
+}
+
+/*
+ * Run a single migration benchmark
+ * fd: file descriptor for hmm device
+ * use_thp: whether to use THP
+ * buffer_size: size of buffer to allocate
+ * iterations: number of iterations
+ * results: where to store results
+ */
+static inline int run_migration_benchmark(int fd, int use_thp, size_t buffer_size,
+					   int iterations, struct benchmark_results *results)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages = buffer_size / sysconf(_SC_PAGESIZE);
+	double start, end;
+	double s2d_total = 0, d2s_total = 0;
+	int ret, i;
+	int *ptr;
+
+	buffer = hmm_buffer_alloc(buffer_size);
+
+	/* Map memory */
+	buffer->ptr = mmap(NULL, buffer_size, PROT_READ | PROT_WRITE,
+			  MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+
+	if (!buffer->ptr)
+		return -1;
+
+	/* Apply THP hint if requested */
+	if (use_thp)
+		ret = madvise(buffer->ptr, buffer_size, MADV_HUGEPAGE);
+	else
+		ret = madvise(buffer->ptr, buffer_size, MADV_NOHUGEPAGE);
+
+	if (ret)
+		return ret;
+
+	/* Initialize memory to make sure pages are allocated */
+	ptr = (int *)buffer->ptr;
+	for (i = 0; i < buffer_size / sizeof(int); i++)
+		ptr[i] = i & 0xFF;
+
+	/* Warmup iteration */
+	ret = hmm_migrate_sys_to_dev(fd, buffer, npages);
+	if (ret)
+		return ret;
+
+	ret = hmm_migrate_dev_to_sys(fd, buffer, npages);
+	if (ret)
+		return ret;
+
+	/* Benchmark iterations */
+	for (i = 0; i < iterations; i++) {
+		/* System to device migration */
+		start = get_time_ms();
+
+		ret = hmm_migrate_sys_to_dev(fd, buffer, npages);
+		if (ret)
+			return ret;
+
+		end = get_time_ms();
+		s2d_total += (end - start);
+
+		/* Device to system migration */
+		start = get_time_ms();
+
+		ret = hmm_migrate_dev_to_sys(fd, buffer, npages);
+		if (ret)
+			return ret;
+
+		end = get_time_ms();
+		d2s_total += (end - start);
+	}
+
+	/* Calculate average times and throughput */
+	results->sys_to_dev_time = s2d_total / iterations;
+	results->dev_to_sys_time = d2s_total / iterations;
+	results->throughput_s2d = (buffer_size / (1024.0 * 1024.0 * 1024.0)) /
+				 (results->sys_to_dev_time / 1000.0);
+	results->throughput_d2s = (buffer_size / (1024.0 * 1024.0 * 1024.0)) /
+				 (results->dev_to_sys_time / 1000.0);
+
+	/* Cleanup */
+	hmm_buffer_free(buffer);
+	return 0;
+}
+
+/*
+ * Benchmark THP migration with different buffer sizes
+ */
+TEST_F_TIMEOUT(hmm, benchmark_thp_migration, 120)
+{
+	struct benchmark_results thp_results, regular_results;
+	size_t thp_size = 2 * 1024 * 1024; /* 2MB - typical THP size */
+	int iterations = 5;
+
+	printf("\nHMM THP Migration Benchmark\n");
+	printf("---------------------------\n");
+	printf("System page size: %ld bytes\n", sysconf(_SC_PAGESIZE));
+
+	/* Test different buffer sizes */
+	size_t test_sizes[] = {
+		thp_size / 4,      /* 512KB - smaller than THP */
+		thp_size / 2,      /* 1MB - half THP */
+		thp_size,          /* 2MB - single THP */
+		thp_size * 2,      /* 4MB - two THPs */
+		thp_size * 4,      /* 8MB - four THPs */
+		thp_size * 8,       /* 16MB - eight THPs */
+		thp_size * 128,       /* 256MB - one twenty eight THPs */
+	};
+
+	static const char *const test_names[] = {
+		"Small Buffer (512KB)",
+		"Half THP Size (1MB)",
+		"Single THP Size (2MB)",
+		"Two THP Size (4MB)",
+		"Four THP Size (8MB)",
+		"Eight THP Size (16MB)",
+		"One twenty eight THP Size (256MB)"
+	};
+
+	int num_tests = ARRAY_SIZE(test_sizes);
+
+	/* Run all tests */
+	for (int i = 0; i < num_tests; i++) {
+		/* Test with THP */
+		ASSERT_EQ(run_migration_benchmark(self->fd, 1, test_sizes[i],
+					iterations, &thp_results), 0);
+
+		/* Test without THP */
+		ASSERT_EQ(run_migration_benchmark(self->fd, 0, test_sizes[i],
+					iterations, &regular_results), 0);
+
+		/* Print results */
+		print_benchmark_results(test_names[i], test_sizes[i],
+					&thp_results, &regular_results);
+	}
+}
 TEST_HARNESS_MAIN
-- 
2.51.0